Introducing Amazon Nova 2 Omni in Preview

Amazon Nova 2 Omni Release

Amazon Nova 2 Omni is an all-in-one model for multimodal reasoning and image generation, supporting text, images, video, and speech inputs while generating both text and image outputs. It enables multimodal understanding, image generation, and editing using natural language, and speech transcription.

Unlike traditional approaches, Nova 2 Omni eliminates the complexity of managing multiple AI models, accelerating application development and reducing complexity and costs.

• Features: Supports 1M token context window, 200+ languages for text processing, and 10 languages for speech input.
• Capabilities: Generates and edits high-quality images using natural language, superior speech understanding, and native reasoning for multi-speaker conversations.
• Flexibility: Offers reasoning controls for depth and budget to ensure optimal performance, accuracy, and cost management.

What to do

• Reach out to your AWS account team for early access.
• Read the user guide for more information.

Source: AWS release notes

If you need further guidance on AWS, our experts are available at AWS@westloop.io. You may also reach us by submitting the Contact Us form.